Intelligent Temperature Regulation Method and Device for Hydraulic Station Cooling System

Abstract

This application provides a method and apparatus for intelligent temperature regulation of a hydraulic station cooling device, relating to the field of cooling regulation technology. The method includes: obtaining basic temperature monitoring data; constructing a temperature transfer model; obtaining temperature distribution information within the station; identifying abnormal temperature distributions; performing cooling transfer analysis based on the temperature transfer model, starting from the hydraulic station cooling device, to obtain a cooling path; performing cooling target location analysis on the abnormal temperature distribution based on the cooling path; and searching for cooling parameters according to the cooling target location analysis to determine cooling temperature regulation control parameters. This application solves the technical problem in existing technologies where reliance on preset cooling power and cooling oil flow rate, coupled with a lack of analysis of temperature differences between different components, leads to poor cooling effects. It achieves precise cooling regulation of the hydraulic station, improving the accuracy and real-time performance of hydraulic station temperature regulation, optimizing cooling efficiency, and reducing energy consumption.

Description

Technical Field

[0001] This application relates to the field of cooling regulation technology, and in particular to a method and device for intelligent temperature regulation of a hydraulic station cooling device. Background Technology

[0002] In modern hydraulic systems, temperature control is one of the key factors in ensuring efficient system operation and extending equipment lifespan. The operating temperature of a hydraulic system typically rises gradually with increasing workload. Excessive temperature can lead to hydraulic oil deterioration, reduced performance of hydraulic components, and even system failure. To prevent these problems, the temperature of the hydraulic power unit must be monitored and controlled.

[0003] Traditional hydraulic power unit cooling methods primarily rely on preset cooling power and cooling oil flow rates. However, this method has certain limitations. First, fixed cooling parameters cannot adapt to the dynamic temperature changes of the hydraulic power unit under different operating conditions, leading to insufficient cooling or excessive cooling energy consumption in some cases. Furthermore, different components within the hydraulic power unit exhibit varying temperature sensitivities due to differences in location, material, and workload. Traditional cooling systems struggle to provide personalized cooling based on these differences, easily resulting in localized overheating or wasted cooling resources.

[0004] In summary, the existing technology suffers from poor cooling performance due to its reliance on preset cooling power and cooling oil flow rate and the lack of analysis on temperature differences among different components. Summary of the Invention

[0005] The purpose of this application is to provide a method and apparatus for intelligent temperature regulation of a hydraulic station cooling device, in order to solve the technical problem in the prior art that the cooling effect is poor due to reliance on preset cooling power and cooling oil flow rate and lack of analysis of temperature differences of different components.

[0006] In view of the above problems, this application provides a method and device for intelligent temperature regulation of hydraulic station cooling device.

[0007] Firstly, this application provides a method for intelligent temperature regulation of a hydraulic station cooling device. This method is implemented using an intelligent temperature regulation device for the hydraulic station cooling device. The method includes: connecting temperature sensors installed at the pump outlet and the return oil pipeline inlet to obtain basic temperature monitoring data; constructing a temperature transfer model, which is obtained through training with sample data and used for analyzing temperature distribution within the hydraulic station; performing standard preprocessing on the basic temperature monitoring data and inputting it into the temperature transfer model to obtain temperature distribution information within the station, the temperature distribution information having node labels for internal components; identifying and analyzing the temperature distribution information and hydraulic station component thresholds, and determining abnormal temperature distributions based on the node labels and temperature deviations of the internal components; performing cooling transfer analysis starting from the hydraulic station cooling device according to the temperature transfer model to obtain a cooling path, and performing cooling target location analysis on the abnormal temperature distribution based on the cooling path; and searching for cooling parameters according to the cooling target location analysis to determine cooling temperature regulation control parameters, the cooling temperature regulation control parameters being a cooling control strategy that maximizes the cooling temperature demand of each abnormal node in the abnormal temperature distribution.

[0008] Secondly, this application also provides an intelligent temperature regulation device for a hydraulic station cooling system, used to execute the intelligent temperature regulation method for a hydraulic station cooling system as described in the first aspect. The intelligent temperature regulation device includes: a temperature monitoring module for connecting temperature sensors installed at the pump outlet and the return oil pipeline inlet to obtain basic temperature monitoring data; a model building module for building a temperature transfer model, which is obtained through training with sample data and used for analyzing the temperature distribution within the hydraulic station; and a temperature distribution analysis module for performing standard preprocessing on the basic temperature monitoring data and then inputting it into the temperature transfer model to obtain temperature distribution information within the station, wherein the temperature distribution information within the station has station elements. The system includes: a component node labeling module; an abnormal temperature identification module, used to identify and analyze the temperature distribution information within the station and the threshold values ​​of the hydraulic station components, and to determine the abnormal temperature distribution based on the component node labels and temperature deviation; a cooling transfer analysis module, used to perform cooling transfer analysis starting from the hydraulic station cooling device according to the temperature transfer model, to obtain the cooling path, and to perform cooling target location analysis on the abnormal temperature distribution based on the cooling path; and a cooling parameter search module, used to search for cooling parameters according to the cooling target location analysis, to determine the cooling temperature adjustment control parameters, wherein the cooling temperature adjustment control parameters are the cooling control strategy that maximizes the cooling temperature demand of each abnormal node in the abnormal temperature distribution.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] Temperature sensors installed at the pump outlet and return oil pipeline inlet are used to obtain basic temperature monitoring data. A temperature transfer model is constructed, which is trained using sample data and used for temperature distribution analysis within the hydraulic station. After standard preprocessing of the basic temperature monitoring data, it is input into the temperature transfer model to obtain temperature distribution information within the station, which includes node labels for station components. Based on the temperature distribution information and hydraulic station component thresholds, abnormal temperature distributions are identified. According to the temperature transfer model, cooling transfer analysis is performed starting from the hydraulic station cooling device to obtain the cooling path. The abnormal temperature distribution is then analyzed for cooling target localization based on the cooling path. Cooling parameters are searched according to the cooling target localization analysis to determine cooling temperature adjustment control parameters. These cooling temperature adjustment control parameters are cooling control strategies that maximize the cooling temperature demand of each abnormal node in the abnormal temperature distribution. By connecting temperature sensors at the pump outlet and the return oil pipeline inlet, basic temperature data is acquired, a temperature transfer model is constructed to analyze the temperature distribution, and abnormal temperatures are identified by combining component thresholds. Then, abnormal areas are located based on the cooling path, cooling parameters are searched, and a cooling control strategy is determined to achieve precise cooling adjustment of the hydraulic station. This results in improved accuracy and real-time performance of hydraulic station temperature regulation, optimized cooling efficiency, and reduced energy consumption.

[0011] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0013] Figure 1 This is a flowchart illustrating the intelligent temperature regulation method for the hydraulic station cooling device of this application.

[0014] Figure 2 This is a schematic diagram of the intelligent temperature regulation device for the hydraulic station cooling system in this application.

[0015] Explanation of reference numerals in the attached figures:

[0016] Temperature monitoring module 11, model building module 12, temperature distribution analysis module 13, abnormal temperature identification module 14, cooling transfer analysis module 15, and cooling parameter search module 16. Detailed Implementation

[0017] This application provides a method and apparatus for intelligent temperature regulation of a hydraulic station cooling device, solving the technical problem in existing technologies where poor cooling performance is caused by reliance on preset cooling power and cooling oil flow rate and a lack of analysis of temperature differences among different components. By connecting temperature sensors to the pump outlet and the return oil pipe inlet, basic temperature data is acquired, a temperature transfer model is constructed for temperature distribution analysis, and abnormal temperatures are identified by combining component thresholds. Then, based on the cooling path, abnormal areas are located, cooling parameters are searched, and a cooling control strategy is determined, achieving precise cooling regulation of the hydraulic station. This improves the accuracy and real-time performance of hydraulic station temperature regulation, optimizes cooling efficiency, and reduces energy consumption.

[0018] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0019] Example 1, please refer to the appendix. Figure 1 This application provides a method for intelligent temperature regulation of a hydraulic station cooling device. The method is applied to an intelligent temperature regulation device for a hydraulic station cooling device, and specifically includes the following steps:

[0020] Step 1: Connect the temperature sensors installed at the pump outlet and the return oil pipeline inlet to obtain basic temperature monitoring data.

[0021] Specifically, the pump acts as a pressure booster in the hydraulic system, and the temperature at its outlet reflects the heat accumulation of the hydraulic oil after pressure changes. Therefore, installing a temperature sensor at the pump outlet helps monitor the rate of temperature rise of the hydraulic oil and its heat dissipation requirements. The return oil inlet refers to the inlet of the pipeline where the hydraulic oil returns to the system. A temperature sensor is installed here to detect the temperature of the hydraulic oil before it returns to the reservoir or cooling device after circulating through the system. The temperature monitoring data at this location reflects the heat changes experienced by the hydraulic oil after passing through multiple working stages throughout the system.

[0022] Based on this, the temperature sensors installed at the pump outlet and the return oil pipeline inlet are connected through existing wireless communication technology. The temperature data collected by the temperature sensors is received and basic temperature monitoring data is generated, providing basic data support for subsequent temperature analysis and control strategy optimization.

[0023] Step 2: Construct a temperature transfer model, which is obtained through training with sample data and used for analyzing the temperature distribution within the hydraulic station.

[0024] Specifically, the purpose of constructing a temperature transfer model is to achieve a comprehensive analysis of the temperature distribution of the entire hydraulic system by analyzing and predicting the temperatures of various components within the hydraulic station. First, the temperature transfer model can be understood as a mathematical model or machine learning model. It simulates how heat is transferred and distributed within the hydraulic system by learning the temperature change patterns at the pump outlet and return oil pipe inlet within the hydraulic station. Using existing machine learning models, such as neural network models, to construct the temperature transfer model, sample data training refers to using historical operating data, with the temperature changes of the hydraulic station under various operating conditions, as samples input into the model for training. The goal of training is to enable the model to learn the temperature change patterns of the hydraulic station under different operating conditions. For example, sample data may include temperature change curves of various components under different ambient temperatures, load conditions, and operating times. After preprocessing, this data is input into the model for regression learning to improve the model's ability to predict temperature distribution. Once the sample data training is complete, the temperature distribution analysis is the model's output. The temperature distribution analysis results mark each component node of the hydraulic station and display the temperature status of each node. By analyzing this data, we can identify which nodes may exhibit abnormal temperature distributions, thereby predicting potential overheating problems and providing a basis for further cooling control strategies.

[0025] Step 3: After performing standard preprocessing on the basic temperature monitoring data, input it into the temperature transfer model to obtain the temperature distribution information within the station. The temperature distribution information within the station has labels for the station's component nodes.

[0026] Specifically, basic temperature monitoring data refers to the raw temperature data acquired from various temperature sensors at the pump outlet and return oil pipeline inlet. This data is unprocessed and may contain noise, inconsistent acquisition frequencies, etc. To ensure that the temperature transfer model can accurately and effectively interpret temperature distribution information, this basic data must undergo standard preprocessing. Standard preprocessing typically includes data cleaning, noise reduction, outlier detection and completion, and data normalization. For example, if a sensor malfunctions and causes data to deviate from the normal range for a certain period, outlier detection algorithms are needed to filter or correct this data. Furthermore, since different sensors may have different data acquisition frequencies, time alignment is also required during preprocessing to ensure that data from all sensors are within the same time window.

[0027] For example, in a hydraulic power unit, the temperature sensor at the pump outlet might collect data once per second, while the sensor at the return oil inlet might collect data once every 10 seconds. A standard preprocessing procedure aligns these two sets of data to ensure consistent data collection at the same point in time. This preprocessed baseline temperature monitoring data is then input into the temperature transfer model. Based on this input data, the temperature transfer model outputs the temperature distribution information within the entire hydraulic power unit. This internal temperature distribution information displays the temperature conditions of each component within the hydraulic power unit and assigns a component node label to each component.

[0028] Component node labels are markings for each critical component in a hydraulic power unit, clearly indicating the specific location of temperature distribution. For example, components in a hydraulic power unit may include hydraulic pumps, coolers, valves, and pipes. Each component has a corresponding node label in the temperature distribution information. These labels enable the system to accurately identify the location of temperature anomalies and perform targeted cooling control.

[0029] Step 4: Based on the temperature distribution information within the station and the threshold values ​​of the hydraulic station components, identify and analyze the abnormal temperature distribution. Based on the node labels and temperature deviations of the components within the station, determine the abnormal temperature distribution.

[0030] Specifically, the temperature distribution information within the hydraulic station refers to the temperature state data generated by the temperature transfer model in the previous step. This data shows the temperature distribution of various components in the hydraulic station. Each component's temperature node is associated with its actual temperature value. To ensure the hydraulic station operates within a safe and efficient temperature range, the temperature distribution information within the station needs to be compared and analyzed with preset hydraulic station component thresholds. Hydraulic station component thresholds are safe operating temperature ranges set for each hydraulic station component. Different components have different safe temperature thresholds due to differences in material, location, and workload. For example, the safe operating temperature of a hydraulic pump may be below 60℃, while the safe operating temperature of a cooler may be below 40℃. When the temperature of a component exceeds its set threshold range, it means that the component is overheating and may require cooling measures.

[0031] During the analysis, abnormal temperature distributions are determined based on the node labels of components within the station and the temperature deviation. The node labels are identifiers assigned to each component in the temperature distribution information, accurately locating each component within the hydraulic station. The temperature deviation is the difference between the component temperature in the station's temperature distribution information and the component's threshold value in the hydraulic station. A larger temperature deviation indicates a greater deviation from the safe temperature range for that component. Adding the component's temperature to the abnormal temperature distribution provides important reference data for subsequent cooling measures and system optimization.

[0032] Step 5: Based on the temperature transfer model, perform cooling transfer analysis starting from the hydraulic station cooling device to obtain the cooling path, and analyze the abnormal temperature distribution to locate the cooling target based on the cooling path.

[0033] Specifically, cooling transfer analysis aims to determine the path and target point in the cooling process. This involves analyzing the heat transfer patterns within the hydraulic station to find the optimal cooling path, ultimately achieving precise cooling of abnormal temperature distributions. A temperature transfer model has already been established to analyze the heat distribution within the hydraulic station. This model not only displays the temperature status of each component but also predicts how heat flows within the hydraulic station. Next, cooling transfer analysis is performed starting with the hydraulic station's cooling device (such as a cooler or radiator), which serves as the source of the cooling process and initiates the circulation of cooling oil. The purpose of cooling transfer analysis is to analyze the flow path of the cooling medium within the hydraulic station, analyze the transfer and dissipation of heat at different nodes, and generate cooling paths—the specific paths the cooling medium takes from the hydraulic station's cooling device through various components within the hydraulic station. For example, hydraulic oil starts from the cooling device, passes through multiple components such as pumps, valves, and pipes. Each component absorbs or dissipates heat along the cooling path, causing the hydraulic oil temperature to gradually decrease.

[0034] After the cooling path is determined, cooling target localization analysis is performed on the abnormal temperature distribution. The purpose of cooling target localization analysis is to identify components in the hydraulic station with poor cooling performance and set cooling targets for these components. Cooling targets typically include parameters such as cooling temperature and cooling location. For example, in a hydraulic station, cooling oil starts from the cooler, flows through pipes to the hydraulic pump, then to the hydraulic valves, and finally back to the cooler. In this cooling path, the cooling oil gradually cools from a high temperature to a lower temperature. Using a temperature transfer model, the temperature of the cooling oil at each node can be accurately predicted. For example, if the cooling oil temperature drops by 10°C when passing the hydraulic pump, but the abnormal temperature distribution shows that the temperature deviation of the hydraulic pump is 15°C, it indicates that the current cooling cannot meet the cooling requirements of this node, and this node is taken as the result of the cooling target localization analysis.

[0035] By analyzing and locating cooling targets based on abnormal temperature distributions, the cooling process can be precisely applied to the components that require cooling, avoiding over-cooling or under-cooling, thereby improving the accuracy of cooling temperature control in the hydraulic station.

[0036] Step 6: Search for cooling parameters according to the cooling target location analysis, and determine the cooling temperature adjustment and control parameters. The cooling temperature adjustment and control parameters are the cooling control strategies that maximize the cooling temperature demand of each abnormal node in the abnormal temperature distribution.

[0037] Specifically, during the analysis of cooling target location, nodes where the cooling effect cannot meet the temperature deviation have been identified, and cooling parameter searches are performed based on these nodes. Cooling parameters typically include cooling power, cooling oil flow rate, and cooling time, which collectively determine the efficiency and effectiveness of the cooling process. Cooling parameter search refers to analyzing different combinations of cooling parameters to find the cooling control strategy that maximizes the cooling temperature requirements of each abnormal node in the abnormal temperature distribution, thus generating cooling temperature regulation control parameters. For example, if the hydraulic pump temperature in the hydraulic station is abnormally high, it is necessary to increase the cooling power, increase the cooling oil flow rate, or extend the cooling time to ensure that the hydraulic pump temperature can quickly drop to within the threshold range of the hydraulic station components.

[0038] The selection of cooling temperature regulation control parameters is not simply about maximizing cooling effect, but about balancing cooling efficiency and energy consumption. Therefore, an optimization model is established to calculate the cooling control strategy that maximizes cooling demand. For example, suppose two components in a hydraulic power unit simultaneously experience temperature anomalies: the hydraulic pump temperature is too high, and the cooler temperature exceeds the safe range. In this case, a cooling parameter search is needed to determine how to allocate cooling resources. If the hydraulic pump temperature anomaly is more severe, the cooling oil flow rate and power of the hydraulic pump are prioritized to quickly reduce its temperature. Simultaneously, to prevent the cooler temperature from rising further, the cooling oil distribution is adjusted to ensure the cooler receives sufficient cooling.

[0039] The final determination of the cooling control strategy is based on maximizing cooling demand, prioritizing the nodes with the most severe temperature anomalies and providing them with the optimal cooling parameter configuration. For example, the cooling control strategy for a hydraulic pump might include increasing the cooling oil flow rate to its maximum value within 30 minutes, while simultaneously increasing the cooling power by 20% to quickly reduce the temperature to normal levels.

[0040] In summary, the process of searching for cooling parameters based on the cooling target positioning analysis ultimately aims to determine the cooling temperature regulation and control parameters. These parameters represent the specific operating parameters of the hydraulic station's cooling device, including the temperature regulation of aggressive cooling systems. By rationally allocating cooling resources, the cooling needs of various abnormal nodes can be effectively addressed, ensuring that the entire hydraulic station operates within a high-efficiency and safe temperature range.

[0041] Furthermore, step two of this application includes:

[0042] A sample dataset is constructed using historical operating data and real-time acquired data from the hydraulic station. This dataset includes temperature changes, component operating parameters, and corresponding environmental parameters under all operating conditions. A multi-component sample set is constructed, using the hydraulic station components as classification centers. Regression learning is then performed on the component operating parameters and temperature changes using these multi-component sample sets to obtain a component temperature analysis submodule. A heat conduction submodule is established based on heat conduction theory. Finally, the component temperature analysis submodule and the heat conduction submodule are fused and connected to construct the temperature transfer model.

[0043] Specifically, a sample dataset is constructed using historical operating data and real-time acquired data from the hydraulic station. This dataset includes temperature variations, component operating parameters, and corresponding environmental parameters of the hydraulic station under various operating conditions. The sample dataset can originate from operating records of the hydraulic station under different loads and ambient temperatures. For example, in a large hydraulic station, historical data might record temperature fluctuations during prolonged operation in high-temperature summer conditions, while real-time acquired data can reflect temperature trends under current operating conditions. By combining historical and real-time data, a comprehensive sample dataset can be constructed, providing a foundation for model training.

[0044] Next, using hydraulic station components as classification centers, a multi-component sample set is constructed. This involves classifying the sample dataset according to different hydraulic station components, such as hydraulic pumps, coolers, and valves. Each component's sample set includes its operating parameters (such as pressure, flow rate, and speed), environmental parameters, and corresponding temperature changes under different conditions. This allows the model to learn the temperature variation patterns of each component under different operating conditions more precisely. Furthermore, regression learning is performed on the component operating parameters and temperature changes using the multi-component sample set. Regression learning is an existing machine learning method used to analyze and predict the relationship between a dependent variable (here, temperature) and independent variables (such as operating parameters and environmental parameters). For example, by performing regression learning on the hydraulic pump sample data, the model can grasp the temperature change trend of the hydraulic pump under different flow rates and pressures. The results of the regression learning will form multiple component temperature analysis sub-modules, each focusing on the temperature prediction of one component.

[0045] Building upon this foundation, a heat conduction submodule is established based on heat conduction theory, which explains how heat is transferred in liquids, solids, or gases. For hydraulic power units, the flow of cooling oil and heat exchange on component surfaces are influenced by heat conduction principles. Therefore, the task of the heat conduction submodule is to simulate these heat transfer processes and incorporate them into the model's calculations. For example, the heat from the hydraulic pump is transferred to adjacent components, which not only generate their own heat but also receive heat from other components, resulting in heat accumulation.

[0046] Finally, the component temperature analysis submodule and the heat conduction submodule are integrated to construct a temperature transfer model. This integration ensures that the model can not only predict temperature changes based on component operating parameters but also take into account heat conduction effects, simulating the dynamic temperature transfer process within the hydraulic station. For example, the model can not only predict the temperature change of a component under specific conditions but also infer how the heat from another component affects the temperature of other components.

[0047] In summary, the process of building a temperature transfer model involves deep learning of historical and real-time data from hydraulic stations, combined with heat conduction theory, to form a comprehensive analysis of complex temperature changes within the hydraulic station. This provides accurate predictive basis for intelligent temperature regulation of the hydraulic station, helping to optimize cooling strategies and improve cooling efficiency and safety.

[0048] Furthermore, this application also includes the following steps:

[0049] Using the temperature monitoring data at the pump outlet and the return oil pipeline inlet, a verification data pair is constructed. Based on the verification data pair, using the temperature monitoring data at the pump outlet as input data and the temperature monitoring data at the return oil pipeline inlet as verification data, the loss value of the temperature transfer model is calculated. According to the loss value calculation results, the parameters of the temperature transfer model are iteratively optimized until the convergence target is met, and the temperature transfer model is determined.

[0050] Specifically, validation data pairs are constructed based on temperature monitoring data collected from the pump outlet and the return oil pipeline inlet. These data reflect the temperature changes of the hydraulic oil inside the hydraulic station. The temperature monitoring data at the pump outlet represents the temperature of the hydraulic oil flowing out after pump pressurization, while the temperature monitoring data at the return oil pipeline inlet shows the temperature of the hydraulic oil after circulating through the entire hydraulic system. The construction of validation data pairs involves combining these two temperature data pairs for subsequent model validation and optimization.

[0051] Next, the temperature monitoring data at the pump outlet is used as input data to predict the temperature distribution of the hydraulic oil after it passes through the hydraulic system, while the temperature data from the return oil pipeline is used as the actual temperature to verify the model's prediction results and evaluate the accuracy of the temperature transfer model. The model's output temperature is compared with the actual temperature data at the inlet of the return oil pipeline, and the difference between the two is evaluated; this difference is the model's loss value.

[0052] The loss value is a standard for evaluating the accuracy of a model. The smaller the loss value, the closer the model's prediction is to the actual result; the larger the loss value, the more likely the model's prediction has errors. Based on the loss value calculation results, the temperature transfer model parameters are iteratively optimized. The iterative optimization process involves continuously adjusting the model's parameters to gradually bring the model's prediction results closer to the actual temperature, thus reducing the loss value. This process is typically achieved using the gradient descent algorithm in machine learning, that is, by repeatedly calculating and adjusting the model parameters to gradually reduce errors. For example, adjusting the influence weight of the thermal conductivity coefficient or component operating parameters on temperature can improve the model's prediction accuracy. Iterative optimization continues until the model's loss value reaches a preset convergence target; that is, when the model's loss value no longer decreases significantly, it indicates that the model has reached its optimal state. At this point, the final temperature transfer model is determined. This model has high prediction accuracy and can accurately reflect the temperature changes within the hydraulic station, providing a reliable predictive basis for temperature regulation of the hydraulic station and a solid foundation for adjusting cooling strategies.

[0053] Furthermore, this application also includes the following steps:

[0054] An environmental sensing import channel and a component parameter IoT import channel are established. The environmental sensing import channel is used to connect environmental parameter monitoring sensors to synchronously import the collected environmental parameters. The component parameter IoT import channel is used to connect the IoT sensing devices of each component of the hydraulic station to synchronously import the collected component operating parameters. The environmental sensing import channel and the component parameter IoT import channel are fitted to the input layer of the temperature transfer model, and a combined input relationship of the model input data is established based on the acquisition timestamps of the environmental parameters and component operating parameters. The combined input relationship is used to match the input time of the model input data with the acquisition timestamps, and the obtained environmental parameters, component operating parameters and model input data are combined to generate combined input data.

[0055] Specifically, establishing environmental sensor import channels and component parameter IoT import channels aims to synchronize all relevant monitoring data into the temperature transfer model in a timely manner, thereby improving the model's accuracy and real-time performance. Firstly, the environmental sensor import channel connects to environmental parameter monitoring sensors to synchronously import environmental parameters such as temperature, humidity, and air pressure from the external environment. Environmental factors significantly affect the temperature changes of the hydraulic station, especially when the hydraulic station is located in an open or enclosed environment. Changes in external temperature and humidity can directly affect the cooling effect of the hydraulic station. For example, in high-temperature environments during summer, the cooling load of the hydraulic station may increase, thus requiring accurate monitoring of the ambient temperature.

[0056] The component parameter IoT import channel connects the IoT sensors of various components in the hydraulic station, importing their operating parameters in real time, such as the pressure, flow rate, and speed of the hydraulic pump, or the power of the cooler. These component operating parameters are core data for the model to calculate temperature distribution, directly reflecting the actual working state of the components under different operating conditions. For example, when the flow rate of the hydraulic pump increases, the temperature of the hydraulic oil may rise. This data is transmitted to the temperature transfer model through IoT devices, helping the model to more accurately predict temperature changes.

[0057] Next, the environmental sensor input channel and the component parameter IoT input channel are fitted to the input layer of the temperature transfer model. This involves mapping and matching the data acquired from environmental and component sensors with the input variables of the temperature transfer model. For example, ambient temperature data may affect the heat dissipation efficiency of the hydraulic station, while the speed and flow rate of the hydraulic pump will affect the temperature change of the hydraulic oil. By connecting this data to the input layer of the temperature transfer model, a global perception of temperature changes inside and outside the hydraulic station can be achieved. Based on the acquisition timestamps of the environmental parameters and component operating parameters, a combined input relationship for the model input data is established. The acquisition timestamp refers to the point in time marked when each data point is acquired. Since environmental and component data may be acquired at different frequencies, these data need to be consistently matched according to their timestamps to ensure that each set of input data reflects the true state at a given moment. For example, the hydraulic pump flow rate data may be updated once per second, while the ambient temperature data may be updated once per minute. Alignment will be performed based on these timestamps so that data from the same point in time can be combined.

[0058] Based on the combined input relationship, environmental parameters, component operating parameters, and model input data are combined to generate combined input data, which includes the current operating status of the hydraulic station and overall information about the external environment. For example, at a certain point in time, the ambient temperature is 35℃, the hydraulic pump flow rate is 200L / min, and the cooler power is 500W. These data will be combined and input into the temperature transfer model to calculate the temperature distribution within the hydraulic station at that moment.

[0059] For example, suppose a hydraulic power unit is located in a hot outdoor environment. Environmental sensors detect an increase in the outside temperature, and the hydraulic pump flow rate also increases. This data is fed into a temperature transfer model through its respective input channels, where it is fitted and combined. Based on this combined data, the model may predict that the hydraulic oil temperature will become too high at a critical point, triggering adjustments to the cooling system. This ensures that internal and external factors are comprehensively considered, generating accurate temperature distribution predictions. This provides a reliable foundation for subsequent cooling strategy optimization and improves the precision of temperature control.

[0060] Furthermore, step five of this application includes:

[0061] Based on the current cooling parameters of the cooler, including cooling power and cooling oil flow rate, the cooling heat is determined. Using the temperature transfer model, heat transfer analysis is performed based on this cooling heat to determine the cooling loss during the transfer, where the cooling heat Q = m·C. P ·ΔT,m is the flow rate of cooling oil, C P ΔT is the specific heat capacity of the cooling oil, ΔT is the temperature difference between the inlet and outlet of the cooling oil, and ΔT is the cooling loss value. i is the path node, k is the thermal conductivity of the cooling oil, h is the convective heat transfer coefficient, A is the surface area of ​​the cooling oil in contact with the outside environment, and T is the thermal conductivity of the cooling oil. i To determine the temperature difference between the cooling oil and the outside environment at the i-th path node; based on the pipeline layout of the hydraulic station, starting from the location of the cooling device, and along the path of hydraulic oil flow, perform point-by-point cooling heat analysis based on the cooling loss value during transmission to obtain the cooling heat at each point; and generate the cooling path based on the cooling heat at each point.

[0062] Specifically, the cooling heat is determined based on the current cooling parameters of the cooler, including cooling power and cooling oil flow rate. Cooling heat refers to the heat removed from the hydraulic oil by the cooler per unit time. Its calculation depends on the hydraulic oil flow rate, specific heat capacity, and the temperature difference between the inlet and outlet of the cooling oil. The formula is: Q = m·C P ·ΔT, where m is the flow rate of the cooling oil, C P ΔT represents the specific heat capacity of the cooling oil, and ΔT represents the temperature difference between the inlet and outlet of the cooling oil.

[0063] Next, a heat transfer analysis is performed using a temperature transfer model based on the cooling heat. The purpose of the heat transfer analysis is to simulate the heat exchange of cooling oil as it flows through pipes and components within the hydraulic station. The cooling oil continuously absorbs and releases heat during its flow, therefore, it is necessary to calculate the cooling losses generated during these processes. The determination of the cooling losses is based on the principles of heat transfer. In the flow path of the hydraulic station, the heat loss of the cooling oil is affected by multiple factors, including the thermal conductivity of the path nodes, the convective heat transfer coefficient, the contact surface area between the cooling oil and the external environment, and the temperature difference between the cooling oil and the external environment. The heat transfer at each path node (such as pumps, valves, pipes, etc.) is calculated using the following formula: Cooling Loss Value i represents the path node in the cooling path, k represents the thermal conductivity of the cooling oil, h represents the convective heat transfer coefficient, A represents the surface area of ​​the cooling oil in contact with the external environment, and T represents the surface area of ​​the cooling oil in contact with the external environment. i Let be the temperature difference between the cooling oil and the outside environment at the i-th path node. This allows us to determine the heat loss at each node. For example, if a path node has a large surface area and a large temperature difference, the cooling oil loss at that node will be more significant.

[0064] After calculating the cooling loss, based on the piping layout of the hydraulic station, starting from the location of the cooling device, a point-by-point analysis of cooling heat is performed along the hydraulic oil flow path. This process simulates the path of hydraulic oil flowing from the cooler through different components such as pumps, valves, and pipes, calculating the heat transfer and loss at each node. For example, the hydraulic oil may lose 5% of its heat when passing through the hydraulic pump and 3% when passing through the valve. These point-by-point cooling heat values ​​are summarized to generate the heat transfer situation in the entire cooling path, i.e., the cooling heat at each point. Finally, based on the cooling heat at each point, a complete cooling path is generated. The cooling path is a flow route diagram of the hydraulic oil from the cooler through various components, reflecting the temperature changes and heat losses of the cooling oil at different nodes. This cooling path can be used to optimize the operation of the cooler, ensuring effective heat transfer and avoiding problems of low cooling efficiency. For example, if the cooling path shows insufficient cooling effect at a certain node, the cooling oil flow rate or power at that node can be adjusted to enhance the local cooling effect.

[0065] Furthermore, step six of this application includes:

[0066] The risk coefficients of the hydraulic station components are obtained, representing the degree of risk impact of the components on the hydraulic station. The distribution of cooling targets, including target cooling temperature and target cooling location, is determined based on the cooling target location analysis. An objective function is constructed with the goal of maximizing the target cooling temperature and minimizing energy consumption. The cooling target distribution is used as a constraint, and the risk coefficients are fitted to the objective function as weighting coefficients, with cooling path transmission losses added, to determine the optimized objective function and construct a search space. Using the search space, a search is performed starting from the current cooling parameters to obtain the optimal control parameters for target evaluation, which are then used as the cooling temperature regulation control parameters.

[0067] Furthermore, the expression for the optimization objective function is: Among them, R i For weighting coefficients, P cooling,i For cooling power, t cooling,i Cooldown time, Q cooling,i For cooling oil flow rate, d(P) cooler ,P i ) represents the distance transmitted through the cooling path, α represents the energy consumption coefficient of the cooling oil flow rate, and β represents the path loss coefficient.

[0068] Specifically, the risk coefficient of each component in a hydraulic power unit measures the degree of risk impact of each component on the overall operation of the hydraulic power unit. It reflects the potential threat to the overall safety, stability, and efficiency of the hydraulic power unit when a component overheats or experiences abnormal temperatures. For example, if the hydraulic pump is the most critical component in the hydraulic power unit, its corresponding risk coefficient may be high; overheating or malfunction could lead to the shutdown of the entire hydraulic power unit. The specific risk coefficient can be configured by professionals in the field based on practical experience.

[0069] Having determined the risk factors of the components, the distribution of cooling targets was determined based on the preceding analysis of cooling target location. The cooling target distribution includes the target cooling temperature and target cooling location for each component. The target cooling temperature refers to the desired component temperature achieved through cooling to ensure the component is in a safe operating condition. The target cooling location refers to the specific position of these components within the hydraulic station, which helps in further determining the cooling path. For example, the hydraulic pump might need to be cooled to 60°C and located at the first node in the cooling path.

[0070] To ensure that the cooling process effectively reduces temperature while minimizing energy consumption, an objective function is constructed with the goal of maximizing the target cooling temperature and minimizing energy consumption. The objective function is a mathematical model that defines the conditions and constraints to be met during the optimization process. This objective function comprehensively considers cooling efficiency and energy utilization, aiming to minimize energy consumption while ensuring that all component temperatures reach the target cooling level.

[0071] To make the objective function more accurate, the distribution of cooling targets is used as a constraint, and the risk coefficient is fitted to the objective function as a weighting factor. The weighting factor assigns different priorities to each component; components with higher risk coefficients have greater weight in the objective function, meaning their cooling requirements will be prioritized. For example, if the risk coefficient of the hydraulic pump is 0.8 and the risk coefficient of the valve is 0.4, optimizing cooling parameters will tend to prioritize meeting the cooling requirements of the hydraulic pump.

[0072] Furthermore, cooling path transfer losses are incorporated into the calculation of the objective function. Cooling path transfer losses refer to the heat loss of cooling oil as it flows through different components and paths due to heat exchange and environmental factors. These losses can lead to reduced cooling efficiency and therefore need to be considered during the optimization process. By including cooling path transfer losses as part of the objective function, the effectiveness of different cooling strategies can be evaluated more comprehensively.

[0073] Next, a search space is constructed based on the optimized objective function. The search space is the range used to find the optimal cooling parameters, including all possible combinations of parameters such as cooling power, cooling time, cooling oil flow rate, and path length. Parameter searches are performed within this search space to find the best cooling solution that minimizes energy consumption while meeting cooling requirements.

[0074] By searching the search space starting with the current cooling parameters, the optimal control parameters for the target system will be obtained. These parameters will then serve as the final cooling temperature regulation control parameters. For example, if the search results show that the cooling efficiency is highest and the energy consumption is lowest when the cooling oil flow rate is 150 L / min and the cooling power is 250 W, then this combination will be used as the control strategy for the hydraulic system in actual cooling operations.

[0075] Furthermore, the expression for the objective function is optimized as follows: Among them, R i For weighting coefficients, P cooling,i For cooling power, t cooling,i Cooldown time, Q cooling,i For cooling oil flow rate, d(P) cooler ,P i Let α be the distance of the cooling path, β be the energy consumption coefficient of the cooling oil flow rate, and β be the path loss coefficient. In summary, by considering multiple factors such as risk coefficient, cooling target, and cooling path transmission loss, the optimal cooling strategy is found through optimizing the objective function. This ensures that the hydraulic station achieves the best balance between energy efficiency and cooling effect, thereby improving the temperature control accuracy of the cooling device.

[0076] In summary, the intelligent temperature regulation method for the hydraulic station cooling device provided in this application has the following technical effects:

[0077] Temperature sensors installed at the pump outlet and return oil pipeline inlet are used to obtain basic temperature monitoring data. A temperature transfer model is constructed, which is trained using sample data and used for temperature distribution analysis within the hydraulic station. After standard preprocessing of the basic temperature monitoring data, it is input into the temperature transfer model to obtain temperature distribution information within the station, which includes node labels for station components. Based on the temperature distribution information and hydraulic station component thresholds, abnormal temperature distributions are identified. According to the temperature transfer model, cooling transfer analysis is performed starting from the hydraulic station cooling device to obtain the cooling path. The abnormal temperature distribution is then analyzed for cooling target localization based on the cooling path. Cooling parameters are searched according to the cooling target localization analysis to determine cooling temperature adjustment control parameters. These cooling temperature adjustment control parameters are cooling control strategies that maximize the cooling temperature demand of each abnormal node in the abnormal temperature distribution. By connecting temperature sensors at the pump outlet and the return oil pipeline inlet, basic temperature data is acquired, a temperature transfer model is constructed to analyze the temperature distribution, and abnormal temperatures are identified by combining component thresholds. Then, abnormal areas are located based on the cooling path, cooling parameters are searched, and a cooling control strategy is determined to achieve precise cooling adjustment of the hydraulic station. This results in improved accuracy and real-time performance of hydraulic station temperature regulation, optimized cooling efficiency, and reduced energy consumption.

[0078] Example 2: Based on the intelligent temperature regulation method for the hydraulic station cooling device in the foregoing examples, and using the same inventive concept, this application also provides an intelligent temperature regulation device for the hydraulic station cooling device. Please refer to the appendix. Figure 2 The intelligent temperature control device for the hydraulic station cooling system includes:

[0079] Temperature monitoring module 11 is used to connect to temperature sensors installed at the pump outlet and the inlet of the return oil pipeline to obtain basic temperature monitoring data.

[0080] The model building module 12 is used to build a temperature transfer model, which is obtained by training through sample data and is used for temperature distribution analysis within the hydraulic station.

[0081] The temperature distribution analysis module 13 is used to perform standard preprocessing on the basic temperature monitoring data, input it into the temperature transfer model, and obtain the temperature distribution information within the station. The temperature distribution information within the station has labels for the station's component nodes.

[0082] The abnormal temperature identification module 14 is used to identify and analyze the temperature distribution information in the station and the threshold of the hydraulic station components, and to determine the abnormal temperature distribution based on the node labels of the components in the station and the temperature deviation.

[0083] The cooling transfer analysis module 15 is used to perform cooling transfer analysis based on the temperature transfer model, starting from the hydraulic station cooling device, to obtain the cooling path, and to perform cooling target location analysis on the abnormal temperature distribution based on the cooling path.

[0084] The cooling parameter search module 16 is used to search for cooling parameters according to the cooling target location analysis, and determine the cooling temperature adjustment control parameters. The cooling temperature adjustment control parameters are the cooling control strategies that maximize the cooling temperature demand of each abnormal node in the abnormal temperature distribution.

[0085] Furthermore, the model building module 12 in the intelligent temperature regulation device of the hydraulic station cooling unit is also used for:

[0086] A sample dataset is constructed using historical operating data and real-time acquired data from the hydraulic station. This dataset includes temperature changes, component operating parameters, and corresponding environmental parameters under all operating conditions. A multi-component sample set is constructed, using the hydraulic station components as classification centers. Regression learning is then performed on the component operating parameters and temperature changes using these multi-component sample sets to obtain a component temperature analysis submodule. A heat conduction submodule is established based on heat conduction theory. Finally, the component temperature analysis submodule and the heat conduction submodule are fused and connected to construct the temperature transfer model.

[0087] Furthermore, the model building module 12 in the intelligent temperature regulation device of the hydraulic station cooling unit is also used for:

[0088] Using the temperature monitoring data at the pump outlet and the return oil pipeline inlet, a verification data pair is constructed. Based on the verification data pair, using the temperature monitoring data at the pump outlet as input data and the temperature monitoring data at the return oil pipeline inlet as verification data, the loss value of the temperature transfer model is calculated. According to the loss value calculation results, the parameters of the temperature transfer model are iteratively optimized until the convergence target is met, and the temperature transfer model is determined.

[0089] Furthermore, the model building module 12 in the intelligent temperature regulation device of the hydraulic station cooling unit is also used for:

[0090] An environmental sensing import channel and a component parameter IoT import channel are established. The environmental sensing import channel is used to connect environmental parameter monitoring sensors to synchronously import the collected environmental parameters. The component parameter IoT import channel is used to connect the IoT sensing devices of each component of the hydraulic station to synchronously import the collected component operating parameters. The environmental sensing import channel and the component parameter IoT import channel are fitted to the input layer of the temperature transfer model, and a combined input relationship of the model input data is established based on the acquisition timestamps of the environmental parameters and component operating parameters. The combined input relationship is used to match the input time of the model input data with the acquisition timestamps, and the obtained environmental parameters, component operating parameters and model input data are combined to generate combined input data.

[0091] Furthermore, the cooling transfer analysis module 15 in the intelligent temperature regulation device of the hydraulic station cooling unit is also used for:

[0092] Based on the current cooling parameters of the cooler, including cooling power and cooling oil flow rate, the cooling heat is determined. Using the temperature transfer model, heat transfer analysis is performed based on this cooling heat to determine the cooling loss during the transfer, where the cooling heat Q = m·C. P ·ΔT,m is the flow rate of cooling oil, C P ΔT is the specific heat capacity of the cooling oil, ΔT is the temperature difference between the inlet and outlet of the cooling oil, and ΔT is the cooling loss value. i is the path node, k is the thermal conductivity of the cooling oil, h is the convective heat transfer coefficient, A is the surface area of ​​the cooling oil in contact with the outside environment, and T is the thermal conductivity of the cooling oil. i To determine the temperature difference between the cooling oil and the outside environment at the i-th path node; based on the pipeline layout of the hydraulic station, starting from the location of the cooling device, and along the path of hydraulic oil flow, perform point-by-point cooling heat analysis based on the cooling loss value during transmission to obtain the cooling heat at each point; and generate the cooling path based on the cooling heat at each point.

[0093] Furthermore, the cooling parameter search module 16 in the intelligent temperature regulation device of the hydraulic station cooling unit is also used for:

[0094] The risk coefficients of the hydraulic station components are obtained, representing the degree of risk impact of the components on the hydraulic station. The distribution of cooling targets, including target cooling temperature and target cooling location, is determined based on the cooling target location analysis. An objective function is constructed with the goal of maximizing the target cooling temperature and minimizing energy consumption. The cooling target distribution is used as a constraint, and the risk coefficients are fitted to the objective function as weighting coefficients, with cooling path transmission losses added, to determine the optimized objective function and construct a search space. Using the search space, a search is performed starting from the current cooling parameters to obtain the optimal control parameters for target evaluation, which are then used as the cooling temperature regulation control parameters.

[0095] Furthermore, the expression for the optimization objective function is: Among them, R i For weighting coefficients, P cooling,i For cooling power, t cooling,i Cooldown time, Q cooling,i For cooling oil flow rate, d(P) cooler ,P i ) represents the distance transmitted through the cooling path, α represents the energy consumption coefficient of the cooling oil flow rate, and β represents the path loss coefficient.

[0096] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Figure 1 The intelligent temperature regulation method and specific examples of the hydraulic station cooling device in Embodiment 1 are also applicable to the intelligent temperature regulation device of the hydraulic station cooling device in this embodiment. Through the foregoing detailed description of the intelligent temperature regulation method of the hydraulic station cooling device, those skilled in the art can clearly understand the intelligent temperature regulation device of the hydraulic station cooling device in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here. As for the device disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant details can be found in the method section.

[0097] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0098] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for intelligent temperature regulation of a hydraulic station cooling device, characterized in that, The intelligent temperature regulation method for the hydraulic station cooling device includes: Temperature sensors are connected to the pump outlet and the return oil pipeline inlet to obtain basic temperature monitoring data; A temperature transfer model is constructed, which is obtained by training through sample data and is used for temperature distribution analysis within the hydraulic station. After standard preprocessing of the basic temperature monitoring data, it is input into the temperature transfer model to obtain the temperature distribution information within the station, which has station component node labels. Based on the temperature distribution information within the station and the threshold values ​​of the hydraulic station components, an abnormal temperature distribution is determined based on the node labels and temperature deviations of the components within the station. Based on the temperature transfer model, a cooling transfer analysis is performed starting from the hydraulic station cooling device to obtain the cooling path. Based on the cooling path, the abnormal temperature distribution is analyzed to locate the cooling target. According to the cooling target location analysis, the cooling parameter search is performed to determine the cooling temperature adjustment control parameters. The cooling temperature adjustment control parameters are the cooling control strategy that maximizes the cooling temperature demand of each abnormal node in the abnormal temperature distribution.

2. The intelligent temperature regulation method for the hydraulic station cooling device as described in claim 1, characterized in that, The construction of the temperature transfer model includes: A sample dataset was constructed using historical operating data and real-time acquired data from the hydraulic station, including temperature changes, component operating parameters, and corresponding environmental parameters under all operating conditions. Using hydraulic station components as the classification center, a multi-component sample set is constructed. Regression learning of component operating parameters and temperature changes is performed using the multi-component sample set to obtain the component temperature analysis sub-module. Based on the theory of heat conduction, a heat conduction submodule is established; The component temperature analysis submodule and the heat conduction submodule are integrated and connected to construct the temperature transfer model.

3. The intelligent temperature regulation method for the hydraulic station cooling device as described in claim 2, characterized in that, The temperature transfer model is constructed, followed by: Using the temperature monitoring data at the pump outlet and the return oil pipeline inlet, a verification data pair is constructed. Based on the verification data pair, the temperature monitoring data at the pump outlet is used as input data, and the temperature monitoring data at the inlet of the return oil pipeline is used as verification to calculate the loss value of the temperature transfer model. Based on the loss value calculation results, the temperature transfer model parameters are iteratively optimized until the convergence target is met, and the temperature transfer model is determined.

4. The intelligent temperature regulation method for the hydraulic station cooling device as described in claim 2, characterized in that, The temperature transfer model is constructed, and then the following steps are also included: An environmental sensing import channel and a component parameter IoT import channel are established. The environmental sensing import channel is used to connect environmental parameter monitoring sensors and synchronously import the collected environmental parameters. The component parameter IoT import channel is used to connect the IoT sensing devices of each component of the hydraulic station and synchronously import the collected component operating parameters. The environmental sensing import channel and the component parameter IoT import channel are fitted to the input layer of the temperature transfer model, and a combined input relationship of the model input data is established according to the acquisition timestamps of the environmental parameters and component operating parameters. The combined input relationship is used to match the input time of the model input data with the acquisition timestamp, and the obtained environmental parameters, component operating parameters and model input data are combined to generate combined input data.

5. The intelligent temperature regulation method for the hydraulic station cooling device as described in claim 1, characterized in that, Based on the temperature transfer model, a cooling transfer analysis is performed starting from the hydraulic station cooling device to obtain the cooling path, including: Based on the current cooling parameters of the cooler, including cooling power and cooling oil flow rate, the cooling heat is determined. Using the temperature transfer model, heat transfer analysis is performed based on this cooling heat to determine the cooling loss during the transfer, where the cooling heat Q = m·C. P ·ΔT,m is the flow rate of cooling oil, C P ΔT is the specific heat capacity of the cooling oil, ΔT is the temperature difference between the inlet and outlet of the cooling oil, and ΔT is the cooling loss value. i is the path node, k is the thermal conductivity of the cooling oil, h is the convective heat transfer coefficient, A is the surface area of ​​the cooling oil in contact with the outside environment, and T is the thermal conductivity of the cooling oil. i The temperature difference between the cooling oil and the outside environment at the i-th path node; Based on the pipeline layout of the hydraulic station, starting from the location of the cooling device, and along the path of hydraulic oil flow, a point-by-point cooling heat analysis is performed based on the cooling loss value in the transmission to obtain the cooling heat at each point. The cooling path is generated based on the cooling heat at each point.

6. The intelligent temperature regulation method for the hydraulic station cooling device as described in claim 5, characterized in that, Based on the cooling target location analysis, a cooling parameter search is performed to determine the cooling temperature regulation and control parameters, including: Obtain the risk coefficient of the hydraulic station components, which is used to represent the degree of risk impact of the components on the hydraulic station; The distribution of cooling targets is determined based on the cooling target location analysis, and the distribution of cooling targets includes cooling target temperature and cooling target location. A target function is constructed with the objective of maximizing the target cooling temperature and minimizing energy consumption. The cooling target distribution is used as a constraint condition, the risk coefficient is used as a weight coefficient and fitted to the objective function, and the cooling path transmission loss is added to determine the optimization objective function and construct the search space. Using the search space, a search is performed starting from the current cooling parameters to obtain the optimal control parameters for the target evaluation, which are then used as the cooling temperature regulation control parameters.

7. The intelligent temperature regulation method for the hydraulic station cooling device as described in claim 6, characterized in that, The expression for the optimization objective function is: min Among them, R i For weighting coefficients, P cooling,i For cooling power, t cooling,i Cooldown time, Q cooling,i For cooling oil flow rate, d(P) cooler ,P i ) represents the distance transmitted through the cooling path, α represents the energy consumption coefficient of the cooling oil flow rate, and β represents the path loss coefficient.

8. A hydraulic station cooling unit temperature intelligent regulation device, characterized in that, The step of implementing the intelligent temperature regulation method for the hydraulic station cooling device according to any one of claims 1 to 7, wherein the intelligent temperature regulation device for the hydraulic station cooling device comprises: The temperature monitoring module is used to connect to the temperature sensors installed at the pump outlet and the inlet of the return oil pipeline to obtain basic temperature monitoring data. The model building module is used to build a temperature transfer model, which is obtained by training through sample data and is used for temperature distribution analysis within the hydraulic station. The temperature distribution analysis module is used to perform standard preprocessing on the basic temperature monitoring data, input it into the temperature transfer model, and obtain the temperature distribution information within the station. The temperature distribution information within the station has labels for the station's component nodes. An abnormal temperature identification module is used to identify and analyze the temperature distribution information within the station and the threshold values ​​of the hydraulic station components, and to determine the abnormal temperature distribution based on the node labels and temperature deviations of the components within the station. The cooling transfer analysis module is used to perform cooling transfer analysis based on the temperature transfer model, starting from the hydraulic station cooling device, to obtain the cooling path, and to perform cooling target location analysis on the abnormal temperature distribution based on the cooling path. The cooling parameter search module is used to search for cooling parameters according to the cooling target location analysis, and determine the cooling temperature adjustment control parameters. The cooling temperature adjustment control parameters are the cooling control strategies that maximize the cooling temperature demand of each abnormal node in the abnormal temperature distribution.

Images